mlsanityData to 7 Oct 2026

GAIA-2: A Controllable Multi-View Generative World Model for Autonomous Driving

arXiv 2503.20523 ↗First posted 26 Mar 2025cs.CV cs.AI cs.ROcited by 178

On the map: World models → World models for autonomous driving

also in 1 more
Abstract (arXiv)

Generative models offer a scalable and flexible paradigm for simulating complex environments, yet current approaches fall short in addressing the domain-specific requirements of autonomous driving - such as multi-agent interactions, fine-grained control, and multi-camera consistency. We introduce GAIA-2, Generative AI for Autonomy, a latent diffusion world model that unifies these capabilities within a single generative framework. GAIA-2 supports controllable video generation conditioned on a rich set of structured inputs: ego-vehicle dynamics, agent configurations, environmental factors, and road semantics. It generates high-resolution, spatiotemporally consistent multi-camera videos across geographically diverse driving environments (UK, US, Germany). The model integrates both structured conditioning and external latent embeddings (e.g., from a proprietary driving model) to facilitate flexible and semantically grounded scene synthesis. Through this integration, GAIA-2 enables scalable simulation of both common and rare driving scenarios, advancing the use of generative world models as a core tool in the development of autonomous systems. Videos are available at https://wayve.ai/thinking/gaia-2.

Key facts. Cited by 178 papers in the map (data through 7 Oct 2026). Placed in World models for autonomous driving, one of 11 directions in World models. Builds on 45 of its 51 references that are in the map. First posted on arXiv 26 Mar 2025.

Builds on

45 of 51 references.

Closest ancestors · 8

Same direction, newest first

  1. 2025MaskGWM: A Generalizable Driving World Model with Video Mask Reconstruction17 Feb
  2. 2024DreamDrive: Generative 4D Scene Modeling from Street View Images31 Dec
  3. 2024DriveDreamer4D: World Models Are Effective Data Machines for 4D Driving Scene Representation17 Oct
  4. 2024Unleashing Generalization of End-to-End Autonomous Driving with Controllable Long Video Generation3 Jun
  5. 2024Vista: A Generalizable Driving World Model with High Fidelity and Versatile Controllability27 May
  6. 2023Driving into the Future: Multiview Visual Forecasting and Planning with World Model for Autonomous Driving29 Nov
  7. 2023GAIA-1: A Generative World Model for Autonomous Driving29 Sep
  8. 2023DriveDreamer: Towards Real-world-driven World Models for Autonomous Driving18 Sep

Other references · 37

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  5. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  6. 2022Scalable Diffusion Models with Transformerscited by 5,931
  7. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  8. 2022Flow Matching for Generative Modelingcited by 5,426
  9. 2017Neural Discrete Representation Learningcited by 4,650
  10. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,229
  11. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,678
  12. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasetscited by 2,526
25 more
  1. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,618
  2. 2018Towards Accurate Generative Models of Video: A New Metric & Challengescited by 1,204
  3. 2016Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Networkcited by 1,199
  4. 2025Cosmos World Foundation Model Platform for Physical AIcited by 833
  5. 2023Scaling Vision Transformers to 22 Billion Parameterscited by 690
  6. 2021VideoGPT: Video Generation using VQ-VAE and Transformerscited by 651
  7. 2024Movie Gen: A Cast of Media Foundation Modelscited by 614
  8. 2024LTX-Video: Realtime Video Latent Diffusioncited by 549
  9. 2022Phenaki: Variable Length Video Generation From Open Domain Textual Descriptioncited by 475
  10. 2019Making Convolutional Networks Shift-Invariant Againcited by 390
  11. 2022MAGVIT: Masked Generative Video Transformercited by 341
  12. 2022OneFormer: One Transformer to Rule Universal Image Segmentationcited by 327
  13. 2022Transformers are Sample-Efficient World Modelscited by 317
  14. 2023Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detectioncited by 313
  15. 2024Diffusion for World Modeling: Visual Details Matter in Ataricited by 285
  16. 2022Long Video Generation with Time-Agnostic VQGAN and Time-Sensitive Transformercited by 244
  17. 2024Deep Compression Autoencoder for Efficient High-Resolution Diffusion Modelscited by 209
  18. 2023Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion modelscited by 199
  19. 2024GEM: A Generalizable Ego-Vision Multimodal World Model for Fine-Grained Ego-Motion, Object Dynamics, and Scene Composition Controlcited by 76
  20. 2021CCVS: Context-aware Controllable Video Synthesiscited by 68
  21. 2022General-purpose, long-context autoregressive modeling with Perceiver ARcited by 60
  22. 2024Fr'echet Video Motion Distance: A Metric for Evaluating Motion Consistency in Videoscited by 54
  23. 2022Temporally Consistent Transformers for Video Generationcited by 43
  24. 2024UniMLVG: Unified Framework for Multi-view Long Video Generation with Comprehensive Control Capabilities for Autonomous Drivingcited by 27
  25. 2022HARP: Autoregressive Latent Video Prediction with High-Fidelity Image Generatorcited by 22

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 62; 2026: 116.

178 papers.

Sort:

By area:

  1. 2025V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planningcited by 738
  2. 2025A Survey of Reinforcement Learning for Large Reasoning Modelscited by 175
  3. 2025Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrievalcited by 157
  4. 2026Advancing Open-source World Modelscited by 144
  5. 2025Genie Envisioner: A Unified World Foundation Platform for Robotic Manipulationcited by 129
  6. 2025Training Agents Inside of Scalable World Modelscited by 122
  7. 2026DreamDojo: A Generalist Robot World Model from Large-Scale Human Videoscited by 117
  8. 2025Controllable Video Generation: A Surveycited by 93
  9. 2025Cosmos-Drive-Dreams: Scalable Synthetic Driving Data Generation with World Foundation Modelscited by 80
  10. 20253D and 4D World Modeling: A Surveycited by 64
  11. 2025GigaWorld-0: World Models as Data Engine to Empower Embodied AIcited by 60
  12. 2025Back to the Features: DINO as a Foundation for Video World Modelscited by 56
38 more
  1. 2025A Survey: Learning Embodied Intelligence from Physical Simulators and World Modelscited by 50
  2. 2025GigaBrain-0: A World Model-Powered Vision-Language-Action Modelcited by 43
  3. 2025DriveLaW:Unifying Planning and Video Generation in a Latent Driving Worldcited by 43
  4. 2025RLVR-World: Training World Models with Reinforcement Learningcited by 38
  5. 2025RoboScape: Physics-informed Embodied World Modelcited by 38
  6. 2025Foundation Models in Autonomous Driving: A Survey on Scenario Generation and Scenario Analysiscited by 37
  7. 2026DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generationcited by 36
  8. 2025From Forecasting to Planning: Policy World Model for Collaborative State-Action Predictioncited by 29
  9. 2025SIMA 2: A Generalist Embodied Agent for Virtual Worldscited by 26
  10. 2026Visuo-Tactile World Modelscited by 26
  11. 2025Critique of World Modelcited by 24
  12. 2025A Survey of Interactive Generative Videocited by 23
  13. 2025What about gravity in video generation? Post-Training Newton's Laws with Verifiable Rewardscited by 23
  14. 2026GigaBrain-0.5M*: a VLA That Learns From World Model-Based Reinforcement Learningcited by 23
  15. 2025WorldLens: Full-Spectrum Evaluations of Driving World Models in Real Worldcited by 22
  16. 2025LEAD: Minimizing Learner-Expert Asymmetry in End-to-End Drivingcited by 22
  17. 2025A Comprehensive Survey on Reinforcement Learning-based Agentic Search: Foundations, Roles, Optimizations, Evaluations, and Applicationscited by 21
  18. 2026DrivingGen: A Comprehensive Benchmark for Generative Video World Models in Autonomous Drivingcited by 20
  19. 2026MultiWorld: Scalable Multi-Agent Multi-View Video World Modelscited by 19
  20. 2025Playing with Transformer at 30+ FPS via Next-Frame Diffusioncited by 18
  21. 2026Learning Query-Specific Rubrics from Human Preferences for DeepResearch Report Generationcited by 18
  22. 2025Orbis: Overcoming Challenges of Long-Horizon Prediction in Driving World Modelscited by 17
  23. 2025AstraNav-World: World Model for Foresight Control and Consistencycited by 17
  24. 2026DriveDreamer-Policy: A Geometry-Grounded World-Action Model for Unified Generation and Planningcited by 17
  25. 2025A Survey of Robotic Navigation and Manipulation with Physics Simulators in the Era of Embodied AIcited by 16
  26. 2025StateSpaceDiffuser: Bringing Long Context to Diffusion World Modelscited by 16
  27. 2025ORV: 4D Occupancy-centric Robot Video Generationcited by 16
  28. 2025Simulating the Visual World with Artificial Intelligence: A Roadmapcited by 15
  29. 2025Dexterous World Modelscited by 15
  30. 2026NVIDIA OmniDreams: Real-Time Generative World Model for Closed-Loop Autonomous Vehicle Simulationcited by 14
  31. 2026Next Forcing: Causal World Modeling with Multi-Chunk Predictioncited by 14
  32. 2026ActWorld: From Explorable to Interactive World Model via Action-Aware Memorycited by 13
  33. 2026Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligencecited by 13
  34. 2025Towards Unified World Models for Visual Navigation via Memory-Augmented Planning and Foresightcited by 11
  35. 2025Learning Interactive World Model for Object-Centric Reinforcement Learningcited by 11
  36. 2025Aerial World Model for Long-horizon Visual Generation and Navigation in 3D Spacecited by 11
  37. 2026When World Models Dream Wrong: Physical-Conditioned Adversarial Attacks against World Modelscited by 11
  38. 2026Subspace-Decomposed JEPAs: Disentangling Progression and Content in Latent World Modelscited by 11

50 most cited of 178 All 178 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Generative AI for Autonomous Driving: A Review
  2. 2025Drive&Gen: Co-Evaluating End-to-End Driving and Video Generation Models
  3. 2024Exploring the Interplay Between Video Generation and World Models in Autonomous Driving: A Survey
  4. 2026X-World: Controllable Ego-Centric Multi-Camera World Models for Scalable End-to-End Driving
  5. 2024DriveArena: A Closed-loop Generative Simulation Platform for Autonomous Driving
  6. 2025A Survey of World Models for Autonomous Driving
  7. 2024DrivingWorld: Constructing World Model for Autonomous Driving via Video GPT
  8. 2025Scenario Dreamer: Vectorized Latent Diffusion for Generating Driving Simulation Environments